This document discusses strong and weak scaling in parallel computing. It explains that Amdahl's law defines the maximum speedup possible for a fixed problem size, posing a bottleneck. Gustafson's law, proposed in 1988, addresses this by analyzing scaled speedup for increasing problem and resource sizes. Under Gustafson's law of weak scaling, scaled speedup grows linearly with processor count as the problem size increases proportionally, avoiding Amdahl's scaling limit.
This document discusses strong and weak scaling in parallel computing. It explains that Amdahl's law defines the maximum speedup possible for a fixed problem size, posing a bottleneck. Gustafson's law, proposed in 1988, addresses this by analyzing scaled speedup for increasing problem and resource sizes. Under Gustafson's law of weak scaling, scaled speedup grows linearly with processor count as the problem size increases proportionally, avoiding Amdahl's scaling limit.
This document discusses strong and weak scaling in parallel computing. It explains that Amdahl's law defines the maximum speedup possible for a fixed problem size, posing a bottleneck. Gustafson's law, proposed in 1988, addresses this by analyzing scaled speedup for increasing problem and resource sizes. Under Gustafson's law of weak scaling, scaled speedup grows linearly with processor count as the problem size increases proportionally, avoiding Amdahl's scaling limit.
Gustafson’s law and weak scaling(1/2) • Amdahl’s law gives the upper limit of speedup for a problem of fixed size. • This seems to be a bottleneck for parallel computing. • Gustafson’s law was proposed in 1988, and is based on the approximations that the parallel part scales linearly with the amount of resources, and that the serial part does not increase with respect to the size of the problem. • It provides the formula for scaled speedup scaled speedup = s + p × N Gustafson’s law and weak scaling (2/2)
• where s, p and N have the same meaning as in Amdahl’s law. With
Gustafson’s law the scaled speedup increases linearly with respect to the number of processors. • There is no upper limit for the scaled speedup. This is called weak scaling, where the scaled speedup is calculated based on the amount of work done for a scaled problem size (in contrast to Amdahl’s law which focuses on fixed problem size).